Benchmark result
perplexity-ai--pplx-computer-qwen-3-6-35b-a3b-mlx-20260709 on Apple M4 Pro — 81.4 tok/s
Measured with oMLX 0.7.0.dev2 on September 13, 2026.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.
How this run compares
1st fastest of 2 runs of this model on Apple M4 Pro · median 80.9 tok/s.
sort
- 181.4tok/s75.8oMLX · KV tq4this run
- 280.4tok/s75.5oMLX · KV tq4
Reproduce this run
tooloMLX 0.7.0.dev2
modelperplexity-ai--pplx-computer-qwen-3-6-35b-a3b-mlx-20260709
context65,536
kv cachetq4
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 1.5 · repetition_penalty 1
clientv0.4.59+97
Set those in oMLX, then:
llm-benchmark benchmark --model "perplexity-ai--pplx-computer-qwen-3-6-35b-a3b-mlx-20260709" --tool "oMLX"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.